Skip to content

[fix] lora benchmarks pass no_lora_flag_cpu #23774

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Sep 17, 2025
Merged

[fix] lora benchmarks pass no_lora_flag_cpu #23774

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6c23808
fix lora benchmarks
dolpm Aug 27, 2025
ebf96d7
Merge branch 'main' into remote/fix-lora-benchmarks
jeejeelee Sep 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion benchmarks/kernels/benchmark_lora.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -464,7 +464,11 @@ def to_device(tensor: torch.Tensor):
for field_name in LoRAKernelMeta.__dataclass_fields__:
field = getattr(self.lora_kernel_meta, field_name)
assert isinstance(field, torch.Tensor)
setattr(self.lora_kernel_meta, field_name, to_device(field))
setattr(
self.lora_kernel_meta,
field_name,
to_device(field) if field_name != "no_lora_flag_cpu" else field,
)

def metadata(self) -> tuple[int, int, int]:
"""
Expand Down Expand Up @@ -512,6 +516,7 @@ def as_lora_shrink_kwargs(self) -> dict[str, Any]:
"lora_token_start_loc": self.lora_kernel_meta.lora_token_start_loc,
"lora_ids": self.lora_kernel_meta.active_lora_ids,
"scaling": 1.0,
"no_lora_flag_cpu": self.lora_kernel_meta.no_lora_flag_cpu,
}

def as_lora_expand_kwargs(self, add_inputs: bool) -> dict[str, Any]:
Expand Down Expand Up @@ -552,6 +557,7 @@ def as_lora_expand_kwargs(self, add_inputs: bool) -> dict[str, Any]:
"lora_ids": self.lora_kernel_meta.active_lora_ids,
"offset_start": 0,
"add_inputs": add_inputs,
"no_lora_flag_cpu": self.lora_kernel_meta.no_lora_flag_cpu,
}

def bench_fn_kwargs(
Expand Down